© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15913
    Prev
    Next
    INDEX
    Explanations

    say proper names

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    qu
    -24.38
    qd
    -23.38
    qua
    -23.00
     Quentin
    -22.38
    quin
    -22.38
    quo
    -21.63
    ql
    -21.50
    _qu
    -21.13
    qm
    -21.00
     quarry
    -20.88
    POSITIVE LOGITS
    匈
    17.13
    皖
    15.81
     Lenin
    15.75
    ė
    15.75
     domination
    15.38
     rus
    15.06
    -ranked
    15.00
    _sock
    15.00
     Henrik
    15.00
    合肥
    14.94
    Activations Density 0.734%

    No Known Activations